Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/googlecloudplatform/cloud-run-mcp/cloud-runnpx skills add GoogleCloudPlatform/cloud-run-mcp --skill cloud-rungit clone --depth 1 https://github.com/GoogleCloudPlatform/cloud-run-mcpWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00010 | $0.00876 |
| Opus 5 | $0.00005 | $0.00438 |
| Sonnet 5 | $0.00002 | $0.00175 |
| Haiku 4.5 | $0.00001 | $0.00088 |
Grade A, and why
cloud-run scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
run (v1)
PREREQUISITE: Ensure you have the
gcloudCLI installed and authenticated withgcloud auth login. Set your project withgcloud config set project [PROJECT_ID].
gcloud run <resource> <method> [flags]
Helper Commands
| Command | Description |
|---|---|
deploy |
Create or update a Cloud Run service or job. |
API Resources
services
list— List available services in the specified region.describe— Obtain details about a given service, such as its URL and configuration.update— Update Cloud Run environment variables, concurrency settings, and other configuration.delete— Delete a service and its associated revisions.update-traffic— Adjust the traffic assignments for a Cloud Run service.proxy— Proxy a service to localhost authenticating as the active account.logs read— Read logs for a Cloud Run service.replace- Create or replace a service from a YAML service specification.add-iam-policy-binding— Add IAM policy binding to a Cloud Run service (e.g., to make it public).remove-iam-policy-binding- Remove IAM policy binding of a Cloud Run service.get-iam-policy- Get the IAM policy for a Cloud Run service.set-iam-policy- Set the IAM policy for a Cloud Run service.
jobs
create— Create a Cloud Run job.execute— Start an execution of a Cloud Run job.list— List available jobs.describe— Obtain details about a given job.deploy- Create or update a Cloud Run jobupdate— Update a Cloud Run job configuration.delete— Delete a Cloud Run job.replace- Create or replace a Cloud Run job from a YAML job specification.executions list— List executions of a Cloud Run job.logs read— Read logs for a Cloud Run job.add-iam-policy-binding— Add IAM policy binding to a Cloud Run job.remove-iam-policy-binding- Remove IAM policy binding of a Cloud Run job.get-iam-policy- Get the IAM policy for a Cloud Run job.set-iam-policy- Set the IAM policy for a Cloud Run job.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 110 lines · 10 tokens per session scan A cbde4c7c9b45
cloud-run is a skill published in the GitHub repository GoogleCloudPlatform/cloud-run-mcp (627 stars, last pushed 12d ago), licensed Apache-2.0. It adds 10 tokens to every session and 876 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
terradart-add-curated-resource
Add or update a curated Google Cloud factory via terradart wrap (schema.json, optional MM YAML, wrapper override, lint, regenerate). Use when extending terradartgoogle with a new google resource.
terradart-backfill-examples
Backfill example quickstarts for curated factories listed in tool/exampledebt.yaml — extend stacks, sync debt, and run terraform validate locally before PR.
terradart-add-beta-resource
Add a beta-only curated factory to terradartgooglebeta (filtered-fixture extraction, googlebeta override, wrap with provider pin). Use when a later provider pin introduces a new beta-only google type — the current pin's beta-only catalog is filled.
terradart-tighten-example-topology
After example backfill, wire orphan factories into sibling refs (SSL certs on proxies, health checks on backends) and run topology + terraform validate gates.
setup-cortex-config
Guides the setup and configuration of the Cortex Framework config.yaml file, validating GCP projects, BigQuery datasets, locations, and Dataform target settings.
build-and-deploy-data-product
Instructions on how to build and deploy a data product in Cortex Framework V7.